A sparse loading-based contribution method for multivariate control performance diagnosis. (January 2020)

• Record Type: Journal Article
• Authors: Wang, Kai; Chen, Junghui; Song, Zhihuan
• Is Part Of: Journal of process control. Volume 85(2020)
• Page Start: 199
• Page End: 213
• Publication Date: 2020-01
• Subjects: Contribution plots -- Control performance diagnosis -- Generalized eigendecomposition -- Sparse loadings; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2019.12.001
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: The data-driven design for control performance diagnosis is considered. The sparse method of the generalized eigen-decomposition issue is proposed. Sparse loadings are used to diagnose the potential root causes. Case studies on the simulated and industrial examples are illustrated. Abstract: An automatic and accurate control performance diagnosis algorithm is necessary for general chemical processes with a number of control loops when a performance change occurs. The popular contribution plots for control performance diagnosis have severe smearing effects of diagnosis and the problems are still not solved. A sparse loading based contribution plot is proposed in this paper to enhance the diagnosis performance. A complete iterative optimization procedure related to how to obtain the sparse loadings is developed. A numerical example and a period of practical industrial data are used to demonstrate the efficiency of the proposed method in comparison with the conventional contribution plots.